Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2589
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing reasons or benefits

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there are" and its variations, indicating existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ointed
    -0.70
     IPM
    -0.64
     wheelchair
    -0.63
    ONSORED
    -0.60
     comprom
    -0.59
     Cum
    -0.56
    oint
    -0.54
     theirs
    -0.53
     Slayer
    -0.51
     Normandy
    -0.51
    POSITIVE LOGITS
    abouts
    1.20
     are
    1.15
     exists
    1.08
    after
    0.99
     ARE
    0.97
     is
    0.96
     aren
    0.96
     needs
    0.93
    upon
    0.92
     seems
    0.92
    Activations Density 0.107%

    No Known Activations